Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution
This work addresses the problem of high costs and technical limitations in drug discovery for researchers by enabling more efficient experimental designs through in-silico hypothesis generation.
The paper tackles the challenge of scaling high-throughput screens to measure cellular responses to many drugs at single-cell resolution by introducing chemCPA, an encoder-decoder architecture that uses transfer learning from bulk RNA datasets to improve generalization, reducing the need for costly single-cell experiments.
Single-cell transcriptomics enabled the study of cellular heterogeneity in response to perturbations at the resolution of individual cells. However, scaling high-throughput screens (HTSs) to measure cellular responses for many drugs remains a challenge due to technical limitations and, more importantly, the cost of such multiplexed experiments. Thus, transferring information from routinely performed bulk RNA HTS is required to enrich single-cell data meaningfully. We introduce chemCPA, a new encoder-decoder architecture to study the perturbational effects of unseen drugs. We combine the model with an architecture surgery for transfer learning and demonstrate how training on existing bulk RNA HTS datasets can improve generalisation performance. Better generalisation reduces the need for extensive and costly screens at single-cell resolution. We envision that our proposed method will facilitate more efficient experiment designs through its ability to generate in-silico hypotheses, ultimately accelerating drug discovery.